Instructions to use t1101675/PICL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use t1101675/PICL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="t1101675/PICL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("t1101675/PICL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use t1101675/PICL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "t1101675/PICL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "t1101675/PICL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/t1101675/PICL
- SGLang
How to use t1101675/PICL with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "t1101675/PICL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "t1101675/PICL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "t1101675/PICL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "t1101675/PICL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use t1101675/PICL with Docker Model Runner:
docker model run hf.co/t1101675/PICL
Add model card
#1
by nielsr HF Staff - opened
This PR adds a model card, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=text-generation.
It also links the model to the paper Pre-Training to Learn in Context, and the Github repository.
t1101675 changed pull request status to merged
Hi @t1101675 thanks for merging!
I noticed that this repo contains a lot of data, would you be able to move that to dedicated dataset repos?
See here for more info on how to make them compatible with the Datasets library (ensuring things like the viewer work): https://huggingface.co/docs/datasets/loading.